4 title => 'charset cheat sheet',
7 "Reference sheet with all glyphs in common character encoding tables,",
8 "and an overview of Unicode ranges and UTF-8 bytes.",
11 charset codepage unicode ascii utf8 latin glyph character encoding
12 reference common overview table
14 stylesheet => [qw'light'],
15 data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
19 <h1>Character encoding</h1>
22 use Shiar_Sheet::FormatChar;
23 my $glyphs = Shiar_Sheet::FormatChar->new;
24 my $cols = 16; # columns
25 my $colsize = 1; # increment per column
27 # generate character table(s)
28 # (~16x faster than decoding in loop;
29 # substr strings is twice as fast as splitting to an array)
31 # default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
32 default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
33 0 => [qw(cp437 -cp863)],
34 1 => [qw(iso-8859-1 -cp1252 -MacRoman -cp850)],
35 2 => [qw(iso-8859-2 -cp1250 -cp852 -MacCentralEurRoman -MacCroatian -MacRumanian)],
36 5 => [qw(koi8-f -iso-8859-5 -cp1251 -MacCyrillic -cp855 -cp866)],
37 7 => [qw(iso-8859-7 -cp1253 -MacGreek -cp737 -cp869)],
38 8 => [qw(iso-8859-8 -cp1255 -MacHebrew -cp862)],
42 my %row = (offset => 0);
44 if ($input =~ s/^--//) {
45 $row{offset} = $endpoint > 160 ? 160 : 48;
47 elsif ($input =~ s/^-//) {
48 $row{offset} = $endpoint > 128 ? 128 : 32;
50 if ($input =~ s/-$//) {
51 $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
54 $row{setnote} = 'over cp437' if $input eq 'cp850';
55 $row{setnote} = 'over iso-8859-1' if $input =~ /^iso-8859-|^cp125/;
58 if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
59 my $start = hex($1) << ($2 ? 4 : 8);
60 my $end = $2 ? hex($2) << 4 : $start + 240;
61 $row{table} = join '', map { chr } $start .. $end+15;
62 utf8::upgrade($row{table}); # prevent latin1 output
63 $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
65 elsif ($input eq 'U') {
66 $row{table} = ' ' x 1024;
67 $row{set} = 'Unicode planes';
68 $row{cell} = do 'charset-ucplanes.inc.pl'
69 or Alert('Table data could not be read', $@ || $!);
72 elsif ($row{set} = Encode::resolve_alias($input)) {
73 if ($row{set} eq 'Internal') {
74 $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
75 $row{set} = 'Unicode BMP';
76 $row{cell} = do 'charset-unicode.inc.pl'
77 or Alert('Table data could not be read', $@ || $!);
79 elsif ($row{set} eq 'utf-8-strict') {
82 $row{cell} = do 'charset-utf8.inc.pl'
83 or Alert('Table data could not be read', $@ || $!);
86 $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
90 Alert("Encoding <q>$input</q> unknown");
92 $row{set} ? \%row : ();
97 } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
98 $Request =~ /\w/ ? split(m{[/+\s]}, $Request) : 'default';
99 my $NOCHAR = chr 0xFFFD;
101 for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
102 substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
103 substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
104 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
105 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
110 my ($table, $offset) = @_;
111 my $def = $table->{$offset} or return;
112 my ($len, $class, $name, $title) = @{$def};
116 $name //= $len <= 2 ? 'res' : 'reserved';
118 if (my $part = $offset/$colsize % $cols) {
120 my $rest = $cols - $part; # remaining
121 $rest = $len if $len < $rest; #TODO: optimise
123 # continued on new row
124 my @next = ($len * $colsize, "$class joinu");
127 push @next, $name, $title;
132 # minority on next row
133 push @next, '"', $title || $name;
135 $table->{$offset + $colsize*$rest} //= \@next;
140 elsif (my $rows = int($len / $cols)) {
142 if ($len -= $rows * $cols) {
143 # partial row remains
144 $table->{$offset + $colsize*$rows * $cols} //= [$len*$colsize, "$class joinu", '', $title];
147 $attr .= sprintf ' rowspan=%d', $rows;
151 $attr .= sprintf ' colspan=%d', $len unless $len == 1;
152 $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
153 $attr .= sprintf ' class="%s"', $class if $class;
154 $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
155 return "<td$attr>$name";
158 for my $row (@request) {
159 printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
160 my $title = $row->{set};
161 $title .= " <aside>($_)</aside>" for $row->{setnote} // ();
162 printf '<caption>%s</caption>', $title;
163 print '<col>' x ($cols + 1);
164 my $coldigits = $colsize * $cols <= 16 ? 1 : 2; # uniform length of hexadecimal header
165 for my $section (qw{thead}) {
166 print "<$section><tr><th>↱";
167 printf '<th>%0*X', $coldigits, $_ * $colsize for 0 .. $cols - 1;
171 for my $msb (0 .. ((length($row->{table}) || 256) - 1) / $cols) {
172 printf '<tr><th>%X', ($msb + int($row->{offset} / $cols)) * $cols * $colsize;
173 for my $lsb (0 .. $cols - 1) {
174 my $val = ( ($msb * $cols) + $lsb ) * $colsize;
176 print range_cell($row->{cell}, $val);
180 my $glyph = substr $row->{table}, $val, 1;
181 if ($glyph eq $NOCHAR) {
186 print "\n".$glyphs->glyph_cell($glyph);
190 say '</table></div>';
197 <table class="glyphs"><tr>
198 <td class="X Cc">control
199 <td class="X Zs"><span>whitespace</span>
200 <td class="X Mn">diacritic<table class="glyphs"><tr>
201 <td class="X Sk">letter
203 <td class="X Po">punctuation<table class="glyphs"><tr>
204 <td class="X Pf">quote
206 <td class="X So">symbol<table class="glyphs"><tr>
207 <td class="X Sm">math
208 <td class="X Sc">currency
210 <td class="X No">numeric
211 <td class="X Greek">greek<table class="glyphs"><tr>
212 <td class="X Latin">latin
213 <td class="X Cyrillic">cyrillic
215 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
216 <td class="X Brahmic">brahmic
217 <td class="X Arabic">arabic
219 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
220 <td class="X African">african
221 <td class="X Hiragana">japanese
222 <td class="X Han">cjk
223 <td class="X Bopomofo">chinese
225 <td class="X Alpha">alphabetic
228 <table class="glyphs"><tr>
229 <td class="X">unicode 7.0
230 <td class="X Xr">proposed
231 <td class="X Xd">deprecated
232 <td class="">unassigned
233 <td class="X Xi">invalid